© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100170
    Prev
    Next
    INDEX
    Explanations

    something granted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benevolence
    0.15
     proble
    0.15
     alm
    0.15
    asida
    0.14
     اوف
    0.14
     fascism
    0.14
    玧
    0.14
     paga
    0.14
    itada
    0.14
     priv
    0.13
    POSITIVE LOGITS
    Z
    0.19
     exerce
    0.17
    З
    0.17
     démarrage
    0.16
    ز
    0.16
    te
    0.16
    }|=
    0.16
    тон
    0.16
    ສົ
    0.16
    riezmann
    0.16
    Activations Density 0.042%

    No Known Activations